Search Results for author:
Found 2 papers, 0 papers with code
Learning a Consensus Sub-Network with Polarization Regularization and One Pass Training
Our method enables pruning and training simultaneously, which saves energy in both the training and inference phases and avoids extra computational overhead from gating modules at inference time.
CV4Code: Sourcecode Understanding via Visual Code Representations
We present CV4Code, a compact and effective computer vision method for sourcecode understanding.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
